基于HSI模型和最大隶属度图像分割算法的研究

Research on image segmentation algorithm based on HSI model and maximum membership degree

本文在提取目标彩色值、背景彩色值的过程中,所使用的方法为图像彩色直方图,借助RGB模型转化手段,构建HSI模型从而建立高斯函数型模糊集,对最大隶属度图像分割算法进行了研究。因HSI模型与人眼视觉效果更接近,通过RGB模型最大隶属度分割算法,本算法分割图片在相似度方面提高7. 45%,在错分率方面提高2. 58%,在速度方面提高2. 12 s,在漏分率方面则有所降低,降低4. 21%,但其正确率为89. 57%,均在接受范围内。

In this paper,in the image color histogram,the background color value and the target color value are extracted directly.The HSI model is formed through the transformation of the RGB model and the Gauss function fuzzy set is established,and the image segmentation algorithm of the maximum membership degree is studied.Because the HSI model is closer to the visual effect of the human eye,the algorithm improves the similarity degree by 7.45%through the maximum membership degree segmentation algorithm of the RGB model,increases the error rate by 2.58%,increases the speed by 2.12 s,reduces the leakage rate and reduces the 4.21%,but its correct rate is 89.57%.Both of them are in the acceptance model.Inside.